CN112339884B - Stabilizer bar arrangement position determining method and device and readable storage medium - Google Patents
Stabilizer bar arrangement position determining method and device and readable storage medium Download PDFInfo
- Publication number
- CN112339884B CN112339884B CN202011023882.5A CN202011023882A CN112339884B CN 112339884 B CN112339884 B CN 112339884B CN 202011023882 A CN202011023882 A CN 202011023882A CN 112339884 B CN112339884 B CN 112339884B
- Authority
- CN
- China
- Prior art keywords
- target
- gap
- stabilizer bar
- adjustable coordinate
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62D—MOTOR VEHICLES; TRAILERS
- B62D65/00—Designing, manufacturing, e.g. assembling, facilitating disassembly, or structurally modifying motor vehicles or trailers, not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60G—VEHICLE SUSPENSION ARRANGEMENTS
- B60G21/00—Interconnection systems for two or more resiliently-suspended wheels, e.g. for stabilising a vehicle body with respect to acceleration, deceleration or centrifugal forces
- B60G21/02—Interconnection systems for two or more resiliently-suspended wheels, e.g. for stabilising a vehicle body with respect to acceleration, deceleration or centrifugal forces permanently interconnected
- B60G21/04—Interconnection systems for two or more resiliently-suspended wheels, e.g. for stabilising a vehicle body with respect to acceleration, deceleration or centrifugal forces permanently interconnected mechanically
- B60G21/05—Interconnection systems for two or more resiliently-suspended wheels, e.g. for stabilising a vehicle body with respect to acceleration, deceleration or centrifugal forces permanently interconnected mechanically between wheels on the same axle but on different sides of the vehicle, i.e. the left and right wheel suspensions being interconnected
- B60G21/055—Stabiliser bars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Combustion & Propulsion (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Chemical & Material Sciences (AREA)
- Transportation (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Manufacturing & Machinery (AREA)
- Vehicle Body Suspensions (AREA)
Abstract
The invention discloses a stabilizer bar arrangement position determining method, a stabilizer bar arrangement position determining device and a readable storage medium, which can effectively reduce development and debugging time of a stabilizer bar. The method comprises the following steps: dividing all peripheral parts into a first target part and a second target part according to the position relation between the target adjustable coordinate section and all the peripheral parts; sequentially adjusting the gaps between the target adjustable coordinate section and the first target part until the gaps between the target adjustable coordinate section and each part meet the requirements; inputting gap data of a target adjustable coordinate section and a first target part which meet the preset gap requirement into a corresponding preset neural network model to obtain a gap between the target adjustable coordinate section and a second target part, wherein the preset neural network model is obtained by training according to the gap data of a designed stabilizer bar and a corresponding peripheral part; and determining the coordinate position of the target adjustable coordinate section according to the gap between the target adjustable coordinate section and the second target part.
Description
Technical Field
The invention relates to the technical field of vehicle stabilizer bar design, in particular to a stabilizer bar arrangement position determining method and device and a readable storage medium.
Background
In the development and design process of a suspension system of a vehicle chassis, the arrangement of the stabilizer bar is mainly limited by peripheral parts (such as an auxiliary frame, a steering machine and the like) of the stabilizer bar, and in order to design a suspension system meeting the requirement, the gap between the stabilizer bar and each peripheral part has different gap requirements.
In the traditional arrangement processing scheme of the stabilizer bar, after the development of peripheral parts of the stabilizer bar is completed, the stabilizer bar is preliminarily adjusted step by step according to the gap requirements of the peripheral parts and the stabilizer bar until the static gap requirements meet the requirements, then the stabilizer bar is analyzed by a Digital Mock Up (DMU), and if the stabilizer bar interferes with the peripheral parts, the adjustment in a refining stage is carried out.
Therefore, in the conventional scheme, the requirement is met by refining and adjusting one step by one step, for example, a certain peripheral part is designed and changed in the research and development process (for example, the appearance structure, the performance target, the cost and other reasons), and the arrangement position of the whole stabilizer bar needs to be changed accordingly, so that the corresponding workload and the research and development time are increased on the basis, the processing process is complicated, and the arrangement and debugging time of the stabilizer bar is too long.
Disclosure of Invention
The invention provides a stabilizer bar arrangement position determining method and device and a readable storage medium, and aims to solve the problem that in the prior art, the development and debugging time of a stabilizer bar is too long.
In a first aspect, there is provided a stabilizer bar arrangement position determination method including:
determining all peripheral parts of a target adjustable coordinate section with a arranged stabilizer bar, wherein the target adjustable coordinate section is an adjustable coordinate section divided according to a hard point node of the arranged stabilizer bar;
dividing all the peripheral parts into a first target part and a second target part according to the position relation between the target adjustable coordinate section and all the peripheral parts;
sequentially adjusting the gaps between the target adjustable coordinate section and each part in the first target part until the gaps between the target adjustable coordinate section and each part meet the preset gap requirement;
inputting the gap data of the target adjustable coordinate section and the first target part which meet the preset gap requirement into a corresponding preset neural network model to obtain the gap between the target adjustable coordinate section and the second target part, wherein the preset neural network model is obtained by training according to the gap data of the designed stabilizer bar and the corresponding peripheral part;
and determining the coordinate position of the target adjustable coordinate section according to the gap between the target adjustable coordinate section and the second target part.
Further, the sequentially adjusting the gaps between the target adjustable coordinate section and each of the first target components includes:
a. determining gaps between target sections of designed stabilizer bars in preset vehicle projects and peripheral parts, wherein the target sections correspond to the target adjustable coordinate sections;
b. classifying gaps between target sections of the designed stabilizer bar and peripheral parts to determine a minimum gap value of each same gap type;
c. selecting one of the first target parts as a reference part;
d. determining whether a gap between the target adjustable coordinate segment and the reference part is less than or equal to the corresponding minimum gap value;
e. if not, prompting a user to adjust according to a corresponding gap requirement so as to adjust the gap between the target adjustable coordinate section and the reference part according to the adjustment operation of the user until the gap is smaller than or equal to the corresponding minimum gap value;
f. if yes, selecting other unselected parts of the first target part as the reference parts, and repeating the steps d-f until all parts in the first target part are selected.
Further, the preset neural network model corresponding to the target adjustable coordinate section is obtained by training in the following training mode:
acquiring gap data of a large number of target sections of designed stabilizer bars and peripheral parts from a designed vehicle project database, wherein the target sections correspond to the target adjustable coordinate sections;
dividing a training set and a verification set from the gap data of the target section and the peripheral parts, wherein the training set comprises training input data and training output data, the training input data comprises the gap data of the target section and the corresponding first target parts, and the training output data is the gap data of the target section and the corresponding second target parts;
training a BP neural network model according to the training input data and the training output data to obtain a target BP neural network model;
verifying a fitting curve output by the target BP neural network model by using the verification set;
and when the target BP neural network model passes the verification, taking the target BP neural network model as a preset neural network model corresponding to the target adjustable coordinate segment.
Furthermore, different preset neural network models correspond to different target adjustable coordinate sections, and model parameters of the preset neural network models corresponding to different target adjustable coordinate sections are different.
Further, the training the BP neural network model according to the training input data and the training output data to obtain the target BP neural network model includes:
training a BP neural network model according to the training input data and the training output data until the learning rate of the BP neural network model is greater than the learning rate corresponding to the target adjustable coordinate section, wherein different target adjustable coordinate sections correspond to different learning;
and taking the BP neural network model with the learning rate larger than the learning rate corresponding to the target adjustable coordinate segment as the target BP neural network model.
In a second aspect, there is provided a stabilizer bar arrangement position determining device including:
the device comprises a first determining module, a second determining module and a third determining module, wherein the first determining module is used for determining all peripheral parts of a target adjustable coordinate section of a arranged stabilizer bar, and the target adjustable coordinate section is an adjustable coordinate section divided according to a hard point node of the arranged stabilizer bar;
the dividing module is used for dividing all the peripheral parts into a first target part and a second target part according to the position relation between the target adjustable coordinate section and all the peripheral parts;
the adjusting module is used for sequentially adjusting the gaps between the target adjustable coordinate section and each part in the first target part until the gaps between the target adjustable coordinate section and each part meet the preset gap requirement;
the acquisition module is used for inputting the gap data of the target adjustable coordinate section and the first target part, which meet the preset gap requirement, into a corresponding preset neural network model so as to acquire the gap between the target adjustable coordinate section and the second target part, wherein the preset neural network model is obtained by training according to the gap data of the designed stabilizer bar and the corresponding peripheral part;
and the second determining module is used for determining the coordinate position of the target adjustable coordinate section according to the gap between the target adjustable coordinate section and the second target part.
Further, the adjusting module is specifically configured to:
a. determining gaps between target sections of designed stabilizer bars in preset vehicle projects and peripheral parts, wherein the target sections correspond to the target adjustable coordinate sections;
b. classifying gaps between target sections of the designed stabilizer bar and peripheral parts to determine a minimum gap value of each same gap type;
c. selecting one of the first target parts as a reference part;
d. determining whether a gap between the target adjustable coordinate segment and the reference part is less than or equal to the corresponding minimum gap value;
e. if not, prompting a user to adjust according to a corresponding gap requirement so as to adjust the gap between the target adjustable coordinate section and the reference part according to the adjustment operation of the user until the gap is smaller than or equal to the corresponding minimum gap value;
f. if yes, selecting other unselected parts of the first target part as the reference parts, and repeating the steps d-f until all parts in the first target part are selected.
In a third aspect, there is provided a stabilizer bar arrangement position determination apparatus including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the above-described stabilizer bar arrangement position determination method when executing the computer program.
A computer-readable storage medium storing a computer program which, when executed by a processor, realizes the steps of the stabilizer bar arrangement position determination method described above.
In one solution provided by the method, the device and the readable storage medium for determining the arrangement position of the stabilizer bar, the stabilizer bar is divided into adjustable coordinate sections which can be used for debugging according to hard nodes of the arranged stabilizer bar, and then each adjustable coordinate section, namely a target adjustable coordinate section, is debugged and arranged one by one, wherein, all peripheral parts of the target adjustable coordinate section are divided, the gap between the target adjustable coordinate section and a first target part is adjusted one by one according to the user operation, for a second target part, the position of the target adjustable coordinate section in the arranged stabilizer bar is known according to the preset neural network trained by utilizing the gap data of the designed stabilizer bar after the gap between the target adjustable coordinate section of the arranged stabilizer bar and the second target part is determined, thereby determining the position of the arranged stabilizer bar to complete the arrangement design of the stabilizer bar. Therefore, according to the scheme, users do not need to debug the stabilizer bars one by one, the complex operation caused by adjusting the gaps one by one is effectively reduced, the debugging process of the arrangement positions is optimized, the design efficiency is effectively improved, and the debugging time of the arrangement positions of the stabilizer bars is reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
Fig. 1 is a schematic view of an application environment of a stabilizer bar arrangement position determining method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a stabilizer bar arrangement position determining method according to an embodiment of the present invention;
FIG. 3 is a schematic drawing showing a portion of a testable coordinate segment of a stabilizer bar according to an embodiment of the present invention;
FIG. 4 is a schematic view of a stabilizer bar and related peripheral components in accordance with an embodiment of the present invention;
fig. 5 is a schematic structural view of a stabilizer bar arrangement position determining device in an embodiment of the present invention;
fig. 6 is another schematic configuration diagram of the stabilizer bar arrangement position determining device in one embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The stabilizer bar arrangement position determining method provided by the embodiment of the invention can be applied to an application environment as shown in fig. 1, and a user side can communicate with a server side through a network to acquire required data, so that the stabilizer bar arrangement position determining method provided by the invention is realized. The user side may be, but is not limited to, various personal computers, notebook computers, tablet computers and other user devices having a display screen, and the user may perform a design for debugging the arrangement position of the stabilizer bar through interaction with the user side, and the user side may implement the method for determining the arrangement position of the stabilizer bar provided by the present invention, which is described in detail below with reference to specific embodiments.
In an embodiment, as shown in fig. 2, a stabilizer bar arrangement position determining method is provided, which is described by taking the example that the method is applied to the user side in fig. 1, and includes the following steps:
s10: determining all peripheral parts of a target adjustable coordinate section of the arranged stabilizer bar, wherein the target adjustable coordinate section is an adjustable coordinate section divided according to the hard point nodes of the arranged stabilizer bar.
In the embodiment of the present invention, for the convenience of description, the stabilizer bar used for adjusting and determining the arrangement position is referred to as an arrangement-stabilized bar. The stabilizer bar is one of components belonging to a vehicle suspension system, and the disposed stabilizer bar has respective hard points including a mounting point of the disposed stabilizer bar, a moving hinge center point and a bushing center point according to different structural characteristics of the designed suspension system. The invention mainly aims to debug and determine the adjustment of the adjustable coordinate section in the arranged stabilizer bar.
For example, as shown in fig. 3, generally, there are 3 suspension hard points in the disposed stabilizer bar, and the disposed stabilizer bar may be divided into 9 segments including 3 segments of hard point segments whose coordinates are not debuggable and 6 segments of adjustable coordinate segments, where the 6 segments of adjustable coordinate segments include segments of (i), (ii), (iii), (iv), (v), and (iv), and when the position of the adjustable coordinate segments is debuggable, each segment of adjustable coordinate segment has a corresponding coordinate for indicating that the currently corresponding segment is located at a position corresponding to the three-dimensional spatial coordinate system, and the 3 segments of coordinates which are not debuggable in fig. 3 are not shown in fig. 3.
It can be understood that the embodiment of the present invention is to perform commissioning and arrangement on the position of each testable coordinate segment where the stabilizer bar is arranged, before all peripheral parts of a target testable coordinate segment where the stabilizer bar is arranged need to be determined, wherein the target testable coordinate segment refers to each testable coordinate segment divided according to the hard point where the stabilizer bar is arranged. Taking fig. 3 as an example, the target adjustable coordinate sections include sections (i), (ii), (iii), (iv), (v), and (iv).
It should be noted that, in practical applications, after the three-dimensional model of the corresponding vehicle is loaded, the position debugging and arranging stage of the arranged stabilizer bar may be entered, and then the positions of the coordinate segments of the arranged stabilizer bar may be initialized according to the initial data of the arranged stabilizer bar, so as to facilitate the user to perform subsequent position debugging and arranging of the adjustable coordinate segments. In the embodiment of the present invention, all peripheral components of the target adjustable coordinate section on which the stabilizer bar is arranged need to be determined. It is understood that peripheral parts of each of the reference sections where the stabilizer bar is disposed may vary depending on the suspension system, and generally, as shown in fig. 4, the peripheral parts where the stabilizer bar is disposed generally include a lower swing arm, a steering rod, a steering gear, a sub-frame, a drive shaft, a wheel, an exhaust pipe, and a vehicle body metal plate.
For example, fig. 4 lists coordinate positions of partial coordinate segments where stabilizer bars are arranged after initialization, based on the positional relationship of the three-dimensional space coordinate system of the stabilizer bar positions arranged, and fig. 4 includes (X ═ 11.018mm Y ═ 2.996mm Z ═ 1.404mm), (X ═ 3.97mm Y ═ 24.18mm Z ═ 0.953mm) (X ═ 17.767mm Y ═ — 2.524mm Z ═ 0mm), and (X ═ 2.863mm Y ═ 7.154mm Z ═ 81.946 mm). Taking the first and second adjustable coordinate sections as an example, all the peripheral parts corresponding to the first and second adjustable coordinate sections generally include an exhaust pipe, a steering engine and an auxiliary frame. It should be noted that all peripheral parts corresponding to the target adjustable coordinate sections corresponding to the same suspension system type are the same, and the present invention can determine all peripheral parts corresponding to the target adjustable coordinate sections on which the stabilizer bars are arranged.
S20: and dividing all the peripheral parts into a first target part and a second target part according to the position relation between the target adjustable coordinate section and all the peripheral parts.
After all peripheral parts of the target adjustable coordinate section where the stabilizer bar is arranged are determined, all the peripheral parts are divided into a first target part and a second target part according to the positional relationship between the target adjustable coordinate section and all the peripheral parts. All the peripheral parts corresponding to the adjustable coordinate sections of different targets have corresponding division modes, can be configured according to experience, and are not limited herein.
For example, taking the first section of the adjustable coordinate section as an example of the target adjustable coordinate section, all peripheral parts of the adjustable coordinate section corresponding to the first section include an exhaust pipe, a steering machine and an auxiliary frame.
It should be noted that, for other adjustable coordinate segments arranged with a stabilizer bar, the processing manner may be analogized, for example, for the second adjustable coordinate segment, a first target component and a second target component corresponding to the second adjustable coordinate segment may also be divided, which is not described herein.
S30: and adjusting the gaps between the target adjustable coordinate section and each part in the first target part in sequence according to user debugging operation until the gaps between the target adjustable coordinate section and each part meet the preset gap requirement.
In the embodiment of the invention, after all the peripheral parts are divided into the first target part and the second target part according to the position relation between the target adjustable coordinate section and all the peripheral parts, the gap between the target adjustable coordinate section and each part in the first target part is adjusted in sequence according to the debugging operation of a user until the gap between the target adjustable coordinate section and each part meets the preset gap requirement. That is, the gap between the target adjustable coordinate segment and the corresponding first target component is adjusted by the user after the position of the disposed stabilizer bar is initialized.
For example, the gap between the segment of the stabilizer bar arranged and the exhaust pipe and the steering machine can be adjusted in sequence until the gap between the segment of the stabilizer bar arranged and the exhaust pipe and the gap between the segment of the stabilizer bar arranged and the steering machine meet the requirements.
S40: and inputting the gap data of the target adjustable coordinate section and the first target part meeting the preset gap requirement into a corresponding preset neural network model so as to obtain the gap between the target adjustable coordinate section and the second target part, wherein the preset neural network model is obtained by training according to the gap data of the designed stabilizer bar and the corresponding peripheral part.
In the embodiment of the invention, the corresponding neural network model is trained in advance for different target adjustable coordinate sections and is used as the preset neural network model corresponding to the target adjustable coordinate section. For example, for the adjustable coordinate segments of the segments I to II, preset neural network models are corresponding to the adjustable coordinate segments.
It should be noted that the preset neural network model corresponding to each target adjustable coordinate segment is obtained by training according to the gap data between the designed stabilizer bar and the corresponding peripheral component, wherein the input and output of the preset neural network model can be determined according to the training strategy during training. In the scheme, the gap data between the corresponding target section of the designed stabilizer bar and the corresponding first target part and the gap data between the corresponding target section of the designed stabilizer bar and the corresponding second target part are used as input, the gap data between the corresponding target section of the designed stabilizer bar and the corresponding second target part is used as output, and model training is carried out, so that the preset neural network model corresponding to the target adjustable coordinate section is obtained. For example, for the preset neural network model corresponding to the testable coordinate section, the gap data between the section of the designed stabilizer bar and the corresponding exhaust pipe and the gap data between the section of the designed stabilizer bar and the subframe are used as input, the gap data between the section of the designed stabilizer bar and the subframe is used as output, model training is performed to obtain a converged model, and the neural network model obtained by training the related gap data of the section of the designed stabilizer bar is used as the preset neural network model corresponding to the section of the arranged stabilizer bar.
It should be noted that, for the obtaining manner of the preset neural network model corresponding to the other adjustable coordinate segments of the arranged stabilizer bar, repeated description is omitted here.
The method comprises the steps of adjusting gaps between a target adjustable coordinate section and each part in a first target part according to user debugging operation in sequence, completing debugging of the gap relation between the target adjustable coordinate section and the corresponding first target part after the gaps between the target adjustable coordinate section and each part meet preset gap requirements, and forming a first debugging position.
For example, after the gap between the section (i) of the stabilizer bar and the exhaust pipe and the steering engine corresponding to the section (i) is adjusted to meet the requirement of the preset gap through user debugging and adjusting operations, the gap data of the exhaust pipe and the steering engine corresponding to the section (i) of the stabilizer bar is acquired and used as the input of the preset neural network model corresponding to the section (i), so that the output of the preset neural network model corresponding to the section (i), namely the gap between the section (i) and the corresponding subframe, can be acquired.
S50: and determining the coordinate position of the target adjustable coordinate section according to the gap between the target adjustable coordinate section and the second target part.
Through the foregoing steps S10-S40, when the gaps between the target adjustable coordinate segment and all the peripheral components (corresponding to the first target component and the second target component) are confirmed, the coordinate position of the target adjustable coordinate segment can be determined according to the gaps between the target adjustable coordinate segment and the second target component.
For example, after the stabilizer (r) segment is laid out and the exhaust pipe, steering gear and subframe positions are determined, the laying position of the stabilizer (r) segment is already tried out. The same applies to the other segments where the stabilizer bar is arranged, thereby completing the arrangement position of the arranged stabilizer bar.
It can be seen that the embodiment of the present invention provides a method for determining an arrangement position of a stabilizer bar, which comprises dividing the stabilizer bar into adjustable coordinate segments for debugging according to hard nodes of the stabilizer bar to be arranged, and sequentially performing position debugging arrangement on each adjustable coordinate segment, i.e. target adjustable coordinate segment one by one, wherein, firstly, all peripheral parts of the target adjustable coordinate segment are divided, the gap between the target adjustable coordinate segment and a first target part is adjusted one by one according to user operation, for a second target part, the position of the target adjustable coordinate segment in the stabilizer bar to be arranged is known according to a preset neural network trained by using the designed gap data of the stabilizer bar, thereby determining the position of the arranged stabilizer bar to complete the arrangement design of the stabilizer bar. Therefore, according to the scheme, a user does not need to debug the stabilizer bars one by one, the complex operation caused by adjusting the gaps one by one is effectively reduced, the arrangement and debugging process of the stabilizer bars is optimized, the design efficiency is effectively improved, and the arrangement and debugging time of the positions of the stabilizer bars is shortened.
Specifically, in an embodiment, an adjusting manner for a gap between a target adjustable coordinate section and a first target component is provided, which specifically includes the following steps a-f:
a. determining gaps between target sections and peripheral parts of designed stabilizer bars in preset vehicle projects, wherein the target sections correspond to the target adjustable coordinate sections.
b. And classifying the gaps between the target sections and the peripheral parts of the designed stabilizer bar to determine the minimum gap value of each same gap type.
For the steps a-b, in order to reduce the time taken for the user to adjust the gap between the target adjustable coordinate section and the corresponding first target component, the gap between the corresponding target section of the designed stabilizer bar and each peripheral component in the preset vehicle project needs to be determined. Specifically, the gap data between the corresponding target segment of the designed stabilizer bar and each peripheral component is acquired in a large number of designed vehicle items, and the gaps between the corresponding target segment of the designed stabilizer bar and each peripheral component are classified to determine the minimum gap value of each same gap type, so that the minimum gap values are convenient for subsequent debugging and adjustment prompts for users.
As a simple example, if there are vehicle item 1 and vehicle item 2, the clearance i1 between section (i) of the stabilizer bar 1 and the corresponding exhaust pipe and the clearance i2 between section (i) and the steering gear in vehicle item 1 are obtained; it is also possible to acquire the clearance i4 of the section (r) of the stabilizer bar 2 and the corresponding exhaust pipe i3 and the section (r) of the steering gear, which have been designed in the vehicle item 2. After sorting the gaps, it can be determined that i1 and i3 are the same gap type and i2 and i4 are the same gap type, thereby determining the minimum gap values in i1 and i3 and the minimum gap values in i2 and i 4. That is, among the clearances of the stabilizer bar and the peripheral parts, the clearances of the same clearance type have been designed to have a corresponding minimum clearance value in the designed vehicle project.
The above examples are merely illustrative, and do not limit the present invention.
c. And selecting one of the first target parts as a reference part.
In this embodiment, one of the first target components corresponding to the first segment of the stabilizer bar will be selected as a reference component. For example, the first target component corresponding to the section of arranging the stabilizer bar is an exhaust pipe and a steering engine, and the exhaust pipe can be selected as a reference component to be firstly subjected to arrangement position debugging.
d. Determining whether a gap between the target adjustable coordinate segment and the reference part is less than or equal to the corresponding minimum gap value.
Still taking the foregoing example as an example, it may be determined whether the gap between the segment of stabilizer bar (r) and the exhaust pipe is arranged to be less than or equal to the corresponding minimum gap value, that is, to determine whether it is less than or equal to the minimum value of i1 and i3 determined in steps a-b.
e. And if not, prompting a user to adjust according to the corresponding gap requirement so as to adjust the gap between the target adjustable coordinate section and the reference part according to the adjustment operation of the user until the gap is less than or equal to the corresponding minimum gap value.
For example, if it is determined that the gap between the segment of the stabilizer bar (r) and the exhaust pipe is greater than the minimum value of i1 and i3, which indicates that the gap between the segment of the stabilizer bar (r) and the exhaust pipe is not designed in the designed vehicle project, the gap between the segment of the stabilizer bar (r) and the exhaust pipe needs to be adjusted, and the user is prompted to adjust according to the corresponding gap requirement until the gap between the segment of the stabilizer bar (r) and the exhaust pipe is less than or equal to the minimum value of i1 and i3 according to the adjustment operation of the user.
It should be noted that, in practical applications, the prompt may be performed in real time through a prompt box in the design interface, for example, the prompt pop-up prompt requires that the adjustable coordinate of the section of the stabilizer bar needs to be moved in the negative X direction (for example, at an interval of 5 mm), and the gap between the section of the stabilizer bar and the exhaust pipe needs to be again required until a condition is met, that is, until it is determined that the gap between the section of the stabilizer bar and the exhaust pipe is less than or equal to the minimum value of i1 and i3, otherwise, the user is prompted to perform gap adjustment.
f. If yes, selecting other unselected parts of the first target part as the reference parts, and repeating the steps d-f until all parts in the first target part are selected.
For example, if it is determined that the gap between the segment of the stabilizer bar arranged and the exhaust pipe is less than or equal to the minimum value of i1 and i3, it is described that the gap between the segment of the stabilizer bar arranged and the exhaust pipe is designed in the designed vehicle project, the gap between the segment of the stabilizer bar arranged and the exhaust pipe does not need to be adjusted, and at this time, other unselected parts of the first target part are selected as reference parts, that is, the steering gear is selected as reference parts, and it is determined whether the gap requirement between the segment of the stabilizer bar arranged and the steering gear is less than the minimum value of i2 and i 4. Similarly, if the gap between the segment (i) of the stabilizer bar and the steering machine is judged to be larger than the minimum value of the i2 and the i4, at this time, it is described that the gap between the segment (i) of the stabilizer bar and the steering machine is not designed in the designed vehicle project, the gap between the segment (i) of the stabilizer bar and the steering machine needs to be adjusted, at this time, adjustment according to the corresponding gap requirement is prompted to the user, so that the gap between the segment (i) of the stabilizer bar and the steering machine is adjusted according to the adjustment operation of the user until the gap is smaller than or equal to the minimum value of the i2 and the i4, and otherwise, the gap adjustment is prompted to the user all the time.
It should be noted that, in practical applications, the prompt may be performed in real time through a prompt box in the design interface, for example, the prompt pop-up prompt requires that the adjustable coordinate of the first segment of the stabilizer bar needs to be moved in the negative Y direction (for example, at 2mm intervals), and the gap between the first segment of the stabilizer bar and the steering gear needs to be arranged again until the condition is met. To this end, all the first target components (exhaust pipe and steering machine) corresponding to the section where the stabilizer bar is arranged are adjusted. Therefore, in the embodiment of the present invention, the relationship between the target adjustable coordinate segment and all the reference parts of the first target part is continuously determined until all the parts in the first target part are adjusted.
It should be noted that, in this embodiment, the process of adjusting the gap between the target adjustable coordinate section and the corresponding first target component is described in the section of arranging the stabilizer bar, and for other target adjustable coordinate sections, the same can be said, which is not illustrated herein.
Therefore, in the embodiment, the debugging interface can be combined, a visual human-computer interaction interface is realized, the position debugging data is processed, the debugging efficiency of each target adjustable coordinate section is improved, and the method is more convenient and fast. It should be noted that, during adjustment, when the gap requirement is not met, the user is continuously prompted to perform corresponding gap adjustment, so that the gap adjustment efficiency is further improved.
In an embodiment, different target adjustable coordinate sections correspond to different preset neural network models, and the preset neural network models corresponding to different target adjustable coordinate sections have different model parameters. Taking the target adjustable coordinate sections of fig. 3 as the first, second, third, fourth, fifth and sixth sections, the first, second, third, fourth, fifth and sixth sections correspond to the preset neural network models, and the model parameters of the preset neural network models corresponding to the first, second, third, fourth, fifth and sixth sections are different.
For example, for the section (i), taking the neural network model adopted for training as the BP neural network model as an example, the number of hidden layers in the network for training the preset neural network model corresponding to the section (i) may be configured to be 10, the output layer to be 2, the maximum training number to be 1000, the training requirement precision to be 1e-5, and the like. It should be noted that, because the requirements and types of peripheral components of different target adjustable coordinate sections in the arranged stabilizer bar are different, the situation of training fitting distortion can be reduced by adopting corresponding model parameters, and the training efficiency and the model accuracy can be improved.
In an embodiment, the preset neural network model corresponding to the target adjustable coordinate segment is obtained by training in the following training mode, including the following steps:
s101: acquiring gap data of a large number of target sections of designed stabilizer bars and peripheral parts from a designed vehicle project database, wherein the target sections correspond to the target adjustable coordinate sections;
for example, taking training of a preset neural network model corresponding to a section of a stabilizer bar arranged in the training process as an example, if a vehicle item 3 and a vehicle item 4 exist, gap data between the section of the vehicle item 3 and a corresponding exhaust pipe, gap data between the section of the vehicle item 3 and a corresponding steering engine, and gap data between the section of the vehicle item 3 and a corresponding subframe can be obtained; and can obtain the clearance data of section I and the corresponding exhaust pipe, the clearance data of section I and the corresponding steering engine and the clearance data of section I and the corresponding auxiliary frame in the stabilizer bar 4 designed in the vehicle item 4. Due to model training requirements, a large number of vehicle items can be acquired to design gap data associated with the stabilizer bar for subsequent model training and validation, and the specific data number is not limited.
S102: and dividing a training set and a verification set from a large number of gap data of the target section and peripheral parts, wherein the training set comprises training input data and training output data, the training input data comprises the gap data of the target section and a corresponding first target part, and the training output data is the gap data of the target section and a corresponding second target part.
For example, in acquiring the data of the clearance between section (r) and the corresponding exhaust pipe, the data of the clearance between section (r) and the corresponding steering gear, and the data of the clearance between section (r) and the corresponding sub-frame in the stabilizer bar 3 designed in the vehicle item 3, and after the clearance data between section (i) and the corresponding exhaust pipe, the clearance data between section (i) and the corresponding steering machine, and the clearance data between section (i) and the corresponding subframe in the stabilizer bar 4 designed in the vehicle item 4 are obtained, a training set for model training and a validation set for model validation are divided from all the acquired data, wherein the training set comprises training input data and training output data, and in a specific application scenario, the training input data includes (r) segment and corresponding tailpipe clearance data for the designed stabilizer bar, and the training output data is the clearance data of the section I of the designed stabilizer bar and the corresponding auxiliary frame.
S103: and training the BP neural network model according to the training input data and the training output data to obtain the target BP neural network model.
S104: and verifying the fitting curve output by the target BP neural network model by using the verification set.
S105: and when the target BP neural network model passes the verification, taking the target BP neural network model as a preset neural network model corresponding to the target adjustable coordinate segment.
For steps S103 to S105, for example, after the gap data of the designed stabilizer bar section and the corresponding exhaust pipe and the gap data of the designed stabilizer bar section and the corresponding subframe are acquired as training input data, and the gap data of the designed stabilizer bar section and the corresponding subframe are acquired as training output data, the BP neural network model is trained according to the training input data and the training output data to acquire the target BP neural network model. That is, in a specific application scenario, the input of the BP neural network model may be designed: the total length is the clearance between the section of the designed stabilizer bar (r) and the subframe + the clearance between the section of the designed stabilizer bar (r) and the exhaust pipe. The output of the BP neural network model is: the gap between the stabilizer bar section and the subframe has been designed. It should be noted that, for other target adjustable coordinate segments, for example, the second segment, when training a corresponding preset neural network model, the input and output of the model during training can be configured according to the actual situation, for example, 2 to 3 inputs and 1 to 2 outputs may be provided, and the specific description is not limited and is not given by way of example.
After the target BP neural network model is trained, a fitting curve output by the target BP neural network model needs to be verified by using a verification set, and when the fitting curve passes the verification, the target BP neural network model is used as a preset neural network model corresponding to a target adjustable coordinate segment. It should be noted that, during model verification, gap data between the segment of the designed stabilizer bar and the exhaust pipe can be input into the target BP neural network model through verification concentration to obtain a model output fitting curve, gap data between the segment of the designed stabilizer bar and the auxiliary frame is obtained by using the fitting curve and is compared with the gap data between the segment of the designed stabilizer bar and the auxiliary frame in the verification set, and when the result is close to or meets the required condition, the output result of the target BP neural network model is accurate, so that the target BP neural network model is used as the preset neural network model corresponding to the segment of the designed stabilizer bar.
For example, the Z-direction coordinates of the section of the arranged stabilizer bar and the subframe are used, a gap between the theoretical section of the arranged stabilizer bar and the subframe is fitted according to a fitting curve a calculated by a preset neural network model corresponding to the section of the stabilizer bar, the gap is compared with the gap between the section of the stabilizer bar and the subframe, a variation is obtained, the Z-point position of the section of the arranged stabilizer bar is adjusted, X, Y, Z coordinates of the section of the stabilizer bar are finally output, the position of the section of the arranged stabilizer bar is determined, and the debugging design of the section of the arranged stabilizer bar is finally completed.
In an embodiment, in step S103, that is, training the BP neural network model according to the training input data and the training output data to obtain the target BP neural network model, the method includes the following steps:
s1031: training a BP neural network model according to the training input data and the training output data until the learning rate of the BP neural network model is greater than the learning rate corresponding to the target adjustable coordinate section, wherein different target adjustable coordinate sections correspond to different learning rates;
s1032: and taking the BP neural network model with the learning rate larger than the learning rate corresponding to the target adjustable coordinate segment as the target BP neural network model.
In the embodiment of the invention, when the preset neural network models corresponding to different target adjustable coordinate sections are trained, different learning rates are provided, the needed target BP neural network model can be conveniently and rapidly obtained, and the model training efficiency can be improved. For example, for the segment (i) with the stabilizer bar, when training the target BP neural network model corresponding to the segment (i) with the stabilizer bar, the learning rate may be set to 0.001, which is not limited herein, and does not limit the learning rates of other segments.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
In one embodiment, there is provided a stabilizer bar arrangement position determination device that corresponds one-to-one to the stabilizer bar arrangement position determination method in the above-described embodiment. As shown in fig. 5, the stabilizer bar arrangement position determination device includes a first determination module 101, a division module 102, an adjustment module 103, an acquisition module 104, and a second determination module. The functional modules are explained in detail as follows:
a first determining module 101, configured to determine all peripheral components of a target adjustable coordinate segment where a stabilizer bar is arranged, where the target adjustable coordinate segment is an adjustable coordinate segment partitioned according to a hard point node where the stabilizer bar is arranged;
a dividing module 102, configured to divide all the peripheral components into a first target component and a second target component according to the position relationships between the target adjustable coordinate segments and all the peripheral components;
the adjusting module 103 is configured to adjust gaps between the target adjustable coordinate section and each of the first target components in sequence according to a user debugging operation until the gaps between the target adjustable coordinate section and each of the components meet a preset gap requirement;
an obtaining module 104, configured to input gap data of the target adjustable coordinate segment and the first target component, which meet the preset gap requirement, into a corresponding preset neural network model, so as to obtain a gap between the target adjustable coordinate segment and the second target component, where the preset neural network model is obtained by training according to gap data of a designed stabilizer bar and a corresponding peripheral component;
a second determining module 105, configured to determine a coordinate position of the target adjustable coordinate section according to a gap between the target adjustable coordinate section and the second target component.
7. The stabilizer bar arrangement position determining apparatus according to claim 6, wherein the adjusting module is specifically configured to:
a. determining gaps between target sections of designed stabilizer bars in preset vehicle projects and peripheral parts, wherein the target sections correspond to the target adjustable coordinate sections;
b. classifying gaps between target sections of the designed stabilizer bar and peripheral parts to determine a minimum gap value of each same gap type;
c. selecting one of the first target parts as a reference part;
d. determining whether a gap between the target adjustable coordinate segment and the reference part is less than or equal to the corresponding minimum gap value;
e. if not, prompting a user to adjust according to a corresponding gap requirement so as to adjust the gap between the target adjustable coordinate section and the reference part according to the adjustment operation of the user until the gap is smaller than or equal to the corresponding minimum gap value;
f. if yes, selecting other unselected parts of the first target part as the reference parts, and repeating the steps d-f until all parts in the first target part are selected.
It can be seen that an embodiment of the present invention provides a stabilizer bar arrangement position determining apparatus, which first divides a stabilizer bar into adjustable coordinate segments for debugging according to hard nodes of the arranged stabilizer bar, and then sequentially performs position debugging arrangement on each adjustable coordinate segment, i.e. a target adjustable coordinate segment one by one, wherein first all peripheral parts of the target adjustable coordinate segment are divided, a gap between the target adjustable coordinate segment and a first target part is adjusted one by one according to a user operation, a second target part is determined by direct output of a preset neural network trained by using gap data of the designed stabilizer bar, after determining a gap between the target adjustable coordinate segment of the arranged stabilizer bar and the second target part, a position of the target adjustable coordinate segment in the arranged stabilizer bar is known, thereby determining the position of the arranged stabilizer bar to complete the arrangement design of the stabilizer bar. Therefore, according to the scheme, a user does not need to debug the stabilizer bars one by one, the complex operation caused by adjusting the gaps one by one is effectively reduced, the arrangement and debugging process of the stabilizer bars is optimized, the design efficiency is effectively improved, and the arrangement and debugging time of the positions of the stabilizer bars is shortened.
As for the specific definition of the stabilizer bar arrangement position determination means, reference may be made to the above definition of the stabilizer bar arrangement position determination method, which is not described herein again. Each module in the stabilizer bar arrangement position determining device described above may be realized in whole or in part by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, there is provided a stabilizer bar arrangement position determination device, which may be a user side, and an internal configuration diagram thereof may be as shown in fig. 6. The stabilizer bar arrangement position determination device includes a processor, a memory, a network interface, a display screen, and an input device connected through a system bus. Wherein the processor of the stabilizer bar arrangement position determination device is configured to provide calculation and control capabilities. The memory of the stabilizer bar arrangement position determination apparatus includes a storage medium, an internal memory. The storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and computer programs in the storage medium to run. The network interface of the stabilizer bar arrangement position determination device is used for communicating with an external server through a network connection. The computer program is executed by a processor to implement a stabilizer bar arrangement position determination method.
In one embodiment, there is provided a stabilizer bar arrangement position determination apparatus including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
determining all peripheral parts of a target adjustable coordinate section with a arranged stabilizer bar, wherein the target adjustable coordinate section is an adjustable coordinate section divided according to a hard point node of the arranged stabilizer bar;
dividing all the peripheral parts into a first target part and a second target part according to the position relation between the target adjustable coordinate section and all the peripheral parts;
adjusting gaps between the target adjustable coordinate section and each part in the first target part in sequence according to user debugging operation until the gaps between the target adjustable coordinate section and each part meet preset gap requirements;
inputting the gap data of the target adjustable coordinate section and the first target part which meet the preset gap requirement into a corresponding preset neural network model to obtain the gap between the target adjustable coordinate section and the second target part, wherein the preset neural network model is obtained by training according to the gap data of the designed stabilizer bar and the corresponding peripheral part;
and determining the coordinate position of the target adjustable coordinate section according to the gap between the target adjustable coordinate section and the second target part.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
determining all peripheral parts of a target adjustable coordinate section with a arranged stabilizer bar, wherein the target adjustable coordinate section is an adjustable coordinate section divided according to a hard point node of the arranged stabilizer bar;
dividing all the peripheral parts into a first target part and a second target part according to the position relation between the target adjustable coordinate section and all the peripheral parts;
adjusting gaps between the target adjustable coordinate section and each part in the first target part in sequence according to user debugging operation until the gaps between the target adjustable coordinate section and each part meet preset gap requirements;
inputting the gap data of the target adjustable coordinate section and the first target part which meet the preset gap requirement into a corresponding preset neural network model to obtain the gap between the target adjustable coordinate section and the second target part, wherein the preset neural network model is obtained by training according to the gap data of the designed stabilizer bar and the corresponding peripheral part;
and determining the coordinate position of the target adjustable coordinate section according to the gap between the target adjustable coordinate section and the second target part.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A stabilizer bar arrangement position determination method characterized by comprising:
determining all peripheral parts of a target adjustable coordinate section with a arranged stabilizer bar, wherein the target adjustable coordinate section is an adjustable coordinate section divided according to a hard point node of the arranged stabilizer bar;
dividing all the peripheral parts into a first target part and a second target part according to the position relation between the target adjustable coordinate section and all the peripheral parts;
sequentially adjusting the gaps between the target adjustable coordinate section and each part in the first target part until the gaps between the target adjustable coordinate section and each part meet the preset gap requirement;
inputting the gap data of the target adjustable coordinate section and the first target part which meet the preset gap requirement into a corresponding preset neural network model to obtain the gap between the target adjustable coordinate section and the second target part, wherein the preset neural network model is obtained by training according to the gap data of the designed stabilizer bar and the corresponding peripheral part;
and determining the coordinate position of the target adjustable coordinate section according to the gap between the target adjustable coordinate section and the second target part.
2. The stabilizer bar arrangement position determination method according to claim 1, wherein the sequentially adjusting the gaps of the target adjustable coordinate section and the respective first target parts includes:
a. determining gaps between target sections of designed stabilizer bars in preset vehicle projects and peripheral parts, wherein the target sections correspond to the target adjustable coordinate sections;
b. classifying gaps between target sections of the designed stabilizer bar and peripheral parts to determine a minimum gap value of each same gap type;
c. selecting one of the first target parts as a reference part;
d. determining whether a gap between the target adjustable coordinate segment and the reference part is less than or equal to the corresponding minimum gap value;
e. if not, prompting a user to adjust according to a corresponding gap requirement so as to adjust the gap between the target adjustable coordinate section and the reference part according to the adjustment operation of the user until the gap is smaller than or equal to the corresponding minimum gap value;
f. if yes, selecting other unselected parts of the first target part as the reference parts, and repeating the steps d-f until all parts in the first target part are selected.
3. The stabilizer bar arrangement position determination method according to claim 1 or 2, wherein the preset neural network model corresponding to the target adjustable coordinate segment is trained in a training manner that:
acquiring gap data of a large number of target sections of designed stabilizer bars and peripheral parts from a designed vehicle project database, wherein the target sections correspond to the target adjustable coordinate sections;
dividing a training set and a verification set from the gap data of the target section and the peripheral parts, wherein the training set comprises training input data and training output data, the training input data comprises the gap data of the target section and the corresponding first target parts, and the training output data is the gap data of the target section and the corresponding second target parts;
training a BP neural network model according to the training input data and the training output data to obtain a target BP neural network model;
verifying a fitting curve output by the target BP neural network model by using the verification set;
and when the target BP neural network model passes the verification, taking the target BP neural network model as a preset neural network model corresponding to the target adjustable coordinate segment.
4. The stabilizer bar arrangement position determination method according to claim 3, wherein different ones of the target adjustable coordinate segments correspond to different preset neural network models, and model parameters of the preset neural network models corresponding to the different ones of the target adjustable coordinate segments are different.
5. The stabilizer bar arrangement position determination method according to claim 3, wherein the training a BP neural network model based on the training input data and the training output data to obtain a target BP neural network model includes:
training a BP neural network model according to the training input data and the training output data until the learning rate of the BP neural network model is greater than the learning rate corresponding to the target adjustable coordinate section, wherein different target adjustable coordinate sections correspond to different learning rates;
and taking the BP neural network model with the learning rate larger than the learning rate corresponding to the target adjustable coordinate segment as the target BP neural network model.
6. A stabilizer bar arrangement position determining apparatus, characterized by comprising:
the device comprises a first determining module, a second determining module and a third determining module, wherein the first determining module is used for determining all peripheral parts of a target adjustable coordinate section of a arranged stabilizer bar, and the target adjustable coordinate section is an adjustable coordinate section divided according to a hard point node of the arranged stabilizer bar;
the dividing module is used for dividing all the peripheral parts into a first target part and a second target part according to the position relation between the target adjustable coordinate section and all the peripheral parts;
the adjusting module is used for sequentially adjusting the gaps between the target adjustable coordinate section and each part in the first target part until the gaps between the target adjustable coordinate section and each part meet the preset gap requirement;
the acquisition module is used for inputting the gap data of the target adjustable coordinate section and the first target part, which meet the preset gap requirement, into a corresponding preset neural network model so as to acquire the gap between the target adjustable coordinate section and the second target part, wherein the preset neural network model is obtained by training according to the gap data of the designed stabilizer bar and the corresponding peripheral part;
and the second determining module is used for determining the coordinate position of the target adjustable coordinate section according to the gap between the target adjustable coordinate section and the second target part.
7. The stabilizer bar arrangement position determining apparatus according to claim 6, wherein the adjusting module is specifically configured to:
a. determining gaps between target sections of designed stabilizer bars in preset vehicle projects and peripheral parts, wherein the target sections correspond to the target adjustable coordinate sections;
b. classifying gaps between target sections of the designed stabilizer bar and peripheral parts to determine a minimum gap value of each same gap type;
c. selecting one of the first target parts as a reference part;
d. determining whether a gap between the target adjustable coordinate segment and the reference part is less than or equal to the corresponding minimum gap value;
e. if not, prompting a user to adjust according to a corresponding gap requirement so as to adjust the gap between the target adjustable coordinate section and the reference part according to the adjustment operation of the user until the gap is smaller than or equal to the corresponding minimum gap value;
f. if yes, selecting other unselected parts of the first target part as the reference parts, and repeating the steps d-f until all parts in the first target part are selected.
8. The stabilizer bar arrangement position determining apparatus according to claim 6 or 7, wherein the corresponding preset neural network model is trained by a training mode of:
acquiring gap data of a large number of target sections of designed stabilizer bars and peripheral parts from a designed vehicle project database, wherein the target sections correspond to the target adjustable coordinate sections;
dividing a training set and a verification set from gap data of a large number of the target segments and peripheral parts, wherein the training set comprises training input data and training output data, the training input data comprises the gap data of the target segments and corresponding first target parts, and the training output data is the gap data of the target segments and corresponding second target parts;
training a BP neural network model according to the training input data and the training output data to obtain a target BP neural network model;
verifying a fitting curve output by the target BP neural network model by using the verification set;
and when the target BP neural network model passes the verification, taking the target BP neural network model as a preset neural network model corresponding to the target adjustable coordinate segment.
9. A stabilizer bar arrangement position determination apparatus comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the stabilizer bar arrangement position determination method according to any one of claims 1 to 5 when executing the computer program.
10. A readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of the stabilizer bar arrangement position determination method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011023882.5A CN112339884B (en) | 2020-09-25 | 2020-09-25 | Stabilizer bar arrangement position determining method and device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011023882.5A CN112339884B (en) | 2020-09-25 | 2020-09-25 | Stabilizer bar arrangement position determining method and device and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112339884A CN112339884A (en) | 2021-02-09 |
| CN112339884B true CN112339884B (en) | 2021-10-29 |
Family
ID=74360345
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011023882.5A Active CN112339884B (en) | 2020-09-25 | 2020-09-25 | Stabilizer bar arrangement position determining method and device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112339884B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008296714A (en) * | 2007-05-30 | 2008-12-11 | Toyota Motor Corp | Suspension design assistant device and suspension design method |
| CN104200040A (en) * | 2014-09-18 | 2014-12-10 | 山东理工大学 | Design method for stiffness matching and diameter of vehicle suspension stabilizer bars |
| CN104573163A (en) * | 2013-10-29 | 2015-04-29 | 广州汽车集团股份有限公司 | Automobile suspension parameterization design method |
| CN104691269A (en) * | 2013-12-06 | 2015-06-10 | 广州汽车集团股份有限公司 | Method and system for designing stabilizer bar of automotive suspension |
| CN108446528A (en) * | 2018-06-01 | 2018-08-24 | 上汽通用五菱汽车股份有限公司 | Front suspension optimum design method, device and computer readable storage medium |
| CN108733934A (en) * | 2018-05-24 | 2018-11-02 | 广东交通职业技术学院 | A kind of simulated automotive chassis refit method and system |
| CN109002577A (en) * | 2018-06-11 | 2018-12-14 | 韶关学院 | A kind of optimization method and system of suspension |
| EP3525115A1 (en) * | 2016-10-04 | 2019-08-14 | JFE Steel Corporation | Method for analyzing optimization of vehicle body joint position, and device |
| CN110443003A (en) * | 2019-08-19 | 2019-11-12 | 合肥工业大学 | A kind of control and optimum design method of active stabilization lever system |
-
2020
- 2020-09-25 CN CN202011023882.5A patent/CN112339884B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008296714A (en) * | 2007-05-30 | 2008-12-11 | Toyota Motor Corp | Suspension design assistant device and suspension design method |
| CN104573163A (en) * | 2013-10-29 | 2015-04-29 | 广州汽车集团股份有限公司 | Automobile suspension parameterization design method |
| CN104691269A (en) * | 2013-12-06 | 2015-06-10 | 广州汽车集团股份有限公司 | Method and system for designing stabilizer bar of automotive suspension |
| CN104200040A (en) * | 2014-09-18 | 2014-12-10 | 山东理工大学 | Design method for stiffness matching and diameter of vehicle suspension stabilizer bars |
| EP3525115A1 (en) * | 2016-10-04 | 2019-08-14 | JFE Steel Corporation | Method for analyzing optimization of vehicle body joint position, and device |
| CN108733934A (en) * | 2018-05-24 | 2018-11-02 | 广东交通职业技术学院 | A kind of simulated automotive chassis refit method and system |
| CN108446528A (en) * | 2018-06-01 | 2018-08-24 | 上汽通用五菱汽车股份有限公司 | Front suspension optimum design method, device and computer readable storage medium |
| CN109002577A (en) * | 2018-06-11 | 2018-12-14 | 韶关学院 | A kind of optimization method and system of suspension |
| CN110443003A (en) * | 2019-08-19 | 2019-11-12 | 合肥工业大学 | A kind of control and optimum design method of active stabilization lever system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112339884A (en) | 2021-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111488640B (en) | Bridge engineering design file generation device, computer equipment and storage medium | |
| CN113110367B (en) | Engine hardware in-loop test method and system | |
| CN107590322B (en) | Drive shaft jumping checking method | |
| CN110096844B (en) | Aerodynamic characteristic optimization design method of non-smooth vehicle surface automobile | |
| Liu et al. | An incremental V-model process for automotive development | |
| JP2014529795A (en) | How to create control unit functions | |
| CN103425842A (en) | Rapid development system and method for parallel robots | |
| CN106022912A (en) | Evaluation model updating method and evaluation model updating system | |
| CN111539066A (en) | Method for parametric integrated design of automobile door cover | |
| KR20150040790A (en) | System and method for prediction of snap-through buckling of formed steel sheet panels | |
| CN112417586A (en) | Body-in-white optimization processing method, device and system for vehicle and storage medium | |
| CN112818462A (en) | Method and device for generating wheel parameter model, storage medium and computer equipment | |
| CN112339884B (en) | Stabilizer bar arrangement position determining method and device and readable storage medium | |
| CN103177165A (en) | Coach body structure design system, coach side overturning simulation test system and method | |
| CN110705159A (en) | Heat source model parameter solving method, device, equipment and storage medium | |
| CN114755974B (en) | Complex structural member machining path optimization method and device, terminal and storage medium | |
| CN111581101A (en) | Software model testing method, device, equipment and medium | |
| CN106709217A (en) | Method for automatically detecting routing angles | |
| CN114218666A (en) | Simulation preprocessing method and device | |
| KR101896112B1 (en) | Integration of CAD and CAE for the optimum design of an automotive part | |
| CN111651904A (en) | Flow field data calculation method and device based on machine learning | |
| Sivashankar et al. | A modeling environment for production powertrain controller development | |
| CN113343366B (en) | Method for determining main section parameters of vehicle body and related equipment | |
| CN112307589A (en) | Unit working condition creating method and device, electronic equipment and storage medium | |
| CN116595768A (en) | Automatic analysis method and device for tire envelope, vehicle and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |